huaxingao commented on code in PR #16006:
URL: https://github.com/apache/iceberg/pull/16006#discussion_r3121132941
##########
arrow/src/test/java/org/apache/iceberg/arrow/vectorized/TestArrowReader.java:
##########
@@ -383,6 +388,133 @@ public void testTimestampMillisAreReadCorrectly() throws
Exception {
assertThat(totalRowsRead).as("Should read all
rows").isEqualTo(millisValues.size());
}
+ private static Stream<Arguments> rejectedUnsignedIntegerCases() {
+ return Stream.of(
+ Arguments.of(
+ 32,
+ PrimitiveType.PrimitiveTypeName.INT32,
+ new Schema(Types.NestedField.optional(1, "col",
Types.IntegerType.get())),
+ "Cannot read UINT32 as an int value"),
+ Arguments.of(
+ 64,
+ PrimitiveType.PrimitiveTypeName.INT64,
+ new Schema(Types.NestedField.optional(1, "col",
Types.LongType.get())),
+ "Cannot read UINT64 as a long value"));
+ }
+
+ @ParameterizedTest
+ @MethodSource("rejectedUnsignedIntegerCases")
+ public void testUnsignedIntegerColumnThrowsException(
+ int unsignedBitWidth,
+ PrimitiveType.PrimitiveTypeName physicalType,
+ Schema schema,
+ String expectedMessage)
+ throws Exception {
+ tables = new HadoopTables();
+ Table table = tables.create(schema, tempDir.toURI() + "/uint" +
unsignedBitWidth);
+
+ MessageType parquetSchema =
+ new MessageType(
+ "test",
+ primitive(physicalType, Type.Repetition.OPTIONAL)
+ .as(LogicalTypeAnnotation.intType(unsignedBitWidth, false))
+ .id(1)
+ .named("col"));
+
+ File testFile =
+ new File(tempDir, "unsigned-int" + unsignedBitWidth + "-" +
System.nanoTime() + ".parquet");
+ try (ParquetWriter<Group> writer =
+ ExampleParquetWriter.builder(new
Path(testFile.toURI())).withType(parquetSchema).build()) {
+ SimpleGroupFactory factory = new SimpleGroupFactory(parquetSchema);
+ Group group = factory.newGroup();
+ if (unsignedBitWidth == 64) {
+ group.add("col", 100L);
+ } else {
+ group.add("col", 100);
+ }
+ writer.write(group);
+ }
+
+ DataFile dataFile =
+ DataFiles.builder(PartitionSpec.unpartitioned())
+ .withPath(testFile.getAbsolutePath())
+ .withFileSizeInBytes(testFile.length())
+ .withFormat(FileFormat.PARQUET)
+ .withRecordCount(1)
+ .build();
+ table.newAppend().appendFile(dataFile).commit();
+
+ assertThatThrownBy(
+ () -> {
+ try (VectorizedTableScanIterable vectorizedReader =
+ new VectorizedTableScanIterable(table.newScan(), 1024,
false)) {
+ for (ColumnarBatch batch : vectorizedReader) {
+ batch.createVectorSchemaRootFromVectors().close();
+ }
+ }
+ })
+ .isInstanceOf(IllegalArgumentException.class)
+ .hasMessageContaining(expectedMessage);
+ }
+
+ @Test
+ public void testUnsignedSmallIntegerColumnRoundtrips() throws Exception {
+ tables = new HadoopTables();
+
+ for (int[] spec : new int[][] {{8, 250}, {16, 50000}}) {
Review Comment:
also change this to @ParameterizedTest?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
